{"id":"W3112925912","doi":"10.1016/j.isprsjprs.2020.11.013","title":"Improving hyperspectral image segmentation by applying inverse noise weighting and outlier removal for optimal scale selection","year":2020,"lang":"en","type":"article","venue":"ISPRS Journal of Photogrammetry and Remote Sensing","topic":"Remote-Sensing Image Classification","field":"Engineering","cited_by":44,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ontario Institute of Technology; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Weighting; Hyperspectral imaging; Outlier; Artificial intelligence; Selection (genetic algorithm); Pattern recognition (psychology); Scale (ratio); Segmentation; Computer science; Noise (video); Computer vision; Image (mathematics); Geography; Cartography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003846466,0.0002213539,0.0003044044,0.0001688661,0.000208968,0.0002175638,0.00005150547,0.0001195065,0.000001274447],"category_scores_gemma":[0.000167419,0.0002234313,0.0001007825,0.0002824865,0.00008350905,0.0004213734,0.00001968195,0.0003801072,6.854105e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001075161,"about_ca_system_score_gemma":0.00002324252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005106078,"about_ca_topic_score_gemma":0.000007650219,"domain_scores_codex":[0.9987268,0.00005092387,0.0004826051,0.0002390558,0.0001979766,0.0003025791],"domain_scores_gemma":[0.9991778,0.00009574323,0.0002629328,0.00007024983,0.0001757961,0.0002175009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006521712,0.000004293272,0.00001403358,0.0001125631,0.00003368922,0.00001364083,0.0006307351,0.0005175086,0.6995955,2.528009e-7,0.0001555398,0.298857],"study_design_scores_gemma":[0.0007432103,0.00009473001,0.00002220668,0.000071223,0.00008995656,0.0006555897,0.001305145,0.671918,0.324499,0.0000144678,0.000411711,0.0001748531],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4954264,0.000236877,0.5037475,0.0001276848,0.0001585716,0.0001978514,0.000002384632,0.00005714196,0.00004559753],"genre_scores_gemma":[0.5043236,0.0001000884,0.4951193,0.00008336386,0.0003122309,7.25365e-8,0.000004728619,0.00004836578,0.000008266706],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6714004,"threshold_uncertainty_score":0.9111264,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01075126544756996,"score_gpt":0.2269801714141491,"score_spread":0.2162289059665792,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}